En este bloque aprenderemos a utilizar herramientas para ajustar los cálculos estadísticos considerando el diseño muestral complejo de la Encuesta Nacional de Salud, Sexualidad y Género (ENSSEX) 2022-2023 en R Exploraremos cómo:
survey y srvyr.La ENSSEX es una encuesta con diseño probabilístico, por lo que que cada encuestado/a tiene una probabilidad de selección conocida. A su vez, para garantizar representatividad se utilizan factores de expansión y estratos de muestreo. Variable relevantes para definir el diseño muestral complejo:
folio_encuestaw_personas_calvarstratvarunitPara más detalle puede revisar el 📄 manual de factores de expansión.
No ajustar por el diseño muestral puede generar errores estándar incorrectos y estimaciones sesgadas.
Para el análisis de los datos de la ENSSEX en R, se pueden utilizar las siguientes librerías:
# Para instalar manualmente
install.packages("tidyverse")
install.packages("rio")
install.packages("haven")
install.packages("survey")
install.packages("srvyr")
# Cargamos las librerías de trabajo
library("tidyverse")
library("rio")
library("haven")
library("survey")
library("srvyr")Abrimos los datos:
# Hay varios caminos para abrir los datos dependiendo el formato:
data <- rio::import("20240516_enssex_data.rdata") # RRevisamos la distribución del ponderador:
summary(data$w_personas_cal) Min. 1st Qu. Median Mean 3rd Qu. Max.
9.885 187.409 372.030 666.173 776.121 4625.366 svydesignLa librería survey escrito por Thomas Lumley permite ajustar análisis estadísticos a diseños muestrales complejos:
Nos permite una aproximación inferencial más precisa a la población (parámetros desconocidos). La función svydesign() define la estructura del muestreo en R.
La estructura estándar del código es:
| Parámetro | Descripción |
|---|---|
id = ~cluster |
Especifica la unidad primaria de muestreo (UPM) (Ej: comunas, hogares). |
strata = ~estrato |
Define los estratos de muestreo (Ej: regiones, grupos socioeconómicos). |
weights = ~ponderador |
Variable con factores de expansión (ponderadores muestrales). |
data = data |
Base de datos de la encuesta. |
nest = TRUE |
Indica que los estratos están anidados en los conglomerados. |
svydesign(id = ~cluster,
strata = ~estrato,
weights = ~ponderador,
data = data,
nest = TRUE
)Definamos el diseño para la ENSSEX
# Definir diseño muestral ENSSEX
enssex_design <- svydesign(
id = ~varunit, # UPM
strata = ~varstrat, # Estratos
weights = ~ w_personas_cal, # Ponderador muestral
data = data,
nest = TRUE,
)
# Revisar el diseño
summary(enssex_design)Stratified 1 - level Cluster Sampling design (with replacement)
With (372) clusters.
svydesign(id = ~varunit, strata = ~varstrat, weights = ~w_personas_cal,
data = data, nest = TRUE, )
Probabilities:
Min. 1st Qu. Median Mean 3rd Qu. Max.
0.0002162 0.0012885 0.0026880 0.0042115 0.0053359 0.1011634
Stratum Sizes:
10111001 10111002 10211001 10311001 10411001 10411002 10511001
obs 432 184 558 307 411 426 307
design.PSU 8 3 10 5 7 8 5
actual.PSU 8 3 10 5 7 8 5
10511002 10611001 10711001 10811001 10811002 10911001 10911002
obs 383 468 582 329 234 636 113
design.PSU 7 9 10 6 4 11 2
actual.PSU 7 9 10 6 4 11 2
11011001 11111001 11211019 11311001 11311002 11311003 11311006
obs 665 321 379 166 281 131 130
design.PSU 12 6 7 3 6 2 2
actual.PSU 12 6 7 3 6 2 2
11311007 11311008 11311011 11311012 11311013 11311015 11311016
obs 89 134 259 103 108 195 156
design.PSU 2 2 5 2 2 4 3
actual.PSU 2 2 5 2 2 4 3
11311018 11311019 11311020 11311021 11311022 11311024 11311026
obs 102 101 331 136 259 133 109
design.PSU 2 2 6 2 5 3 2
actual.PSU 2 2 6 2 5 3 2
11311028 11311029 11311031 11311033 11411001 11511002 11611001
obs 158 175 126 464 385 524 544
design.PSU 3 3 2 9 7 9 10
actual.PSU 3 3 2 9 7 9 10
20211001 20212001 20311001 20313001 20411005 20412001 20511001
obs 248 86 92 131 171 168 298
design.PSU 5 2 2 2 3 3 6
actual.PSU 5 2 2 2 3 3 6
20511002 20512001 20513001 20611001 20612001 20612002 20613001
obs 333 272 120 351 201 217 185
design.PSU 6 5 2 6 4 4 3
actual.PSU 6 5 2 6 4 4 3
20711001 20712001 20712002 20811001 20811002 20811003 20812001
obs 365 209 295 311 366 189 185
design.PSU 6 4 5 6 7 3 3
actual.PSU 6 4 5 6 7 3 3
20812002 20812003 20911001 20912001 20912002 20913001 21011002
obs 170 85 141 215 265 125 363
design.PSU 3 2 3 4 5 2 7
actual.PSU 3 2 3 4 5 2 7
21012001 21012002 21013001 21013002 21112001 21212020 21311001
obs 212 98 99 89 181 72 419
design.PSU 4 2 2 2 3 2 8
actual.PSU 4 2 2 2 3 2 8
21312001 21412001 21413001 21611001 21612001 21613001 21613002
obs 127 202 76 118 226 140 142
design.PSU 3 4 1 2 4 2 2
actual.PSU 3 4 1 2 4 2 2
Data variables:
[1] "folio_encuesta"
[2] "folio_manzana"
[3] "sbj_num"
[4] "region"
[5] "comuna"
[6] "fecha"
[7] "p1"
[8] "p2"
[9] "p3"
[10] "p3_otro"
[11] "p4"
[12] "p5"
[13] "p6"
[14] "p7"
[15] "p8"
[16] "i_1_p9"
[17] "i_2_p9"
[18] "i_3_p9"
[19] "i_4_p9"
[20] "i_5_p9"
[21] "i_6_p9"
[22] "p10"
[23] "i_1_p11"
[24] "i_2_p11"
[25] "i_3_p11"
[26] "i_4_p11"
[27] "i_1_p12"
[28] "i_1_p13"
[29] "i_2_p12"
[30] "i_2_p13"
[31] "i_1_p16"
[32] "i_2_p16"
[33] "i_3_p16"
[34] "i_4_p16"
[35] "i_5_p16"
[36] "i_6_p16"
[37] "i_7_p16"
[38] "i_8_p16"
[39] "i_9_p16"
[40] "i_1_p17"
[41] "i_2_p17"
[42] "i_1_p18a1"
[43] "i_1_p18b1"
[44] "i_1_p18c1"
[45] "i_1_p18d1"
[46] "i_1_p18e1"
[47] "i_2_p18a1"
[48] "i_2_p18b1"
[49] "i_2_p18c1"
[50] "i_2_p18d1"
[51] "i_2_p18e1"
[52] "i_1_p18a2"
[53] "i_1_p18b2"
[54] "i_1_p18c2"
[55] "i_1_p18e2"
[56] "i_1_p18a3"
[57] "i_1_p18b3"
[58] "i_1_p18c3"
[59] "i_1_p18d3"
[60] "i_1_p18e3"
[61] "i_2_p18a3"
[62] "i_2_p18b3"
[63] "i_2_p18c3"
[64] "i_2_p18d3"
[65] "i_2_p18e3"
[66] "i_3_p18a3"
[67] "i_3_p18b3"
[68] "i_3_p18c3"
[69] "i_3_p18d3"
[70] "i_3_p18e3"
[71] "i_4_p18a3"
[72] "i_4_p18b3"
[73] "i_4_p18c3"
[74] "i_4_p18d3"
[75] "i_4_p18e3"
[76] "i_5_p18a3"
[77] "i_5_p18b3"
[78] "i_5_p18c3"
[79] "i_5_p18d3"
[80] "i_5_p18e3"
[81] "p19"
[82] "p20a"
[83] "p20b"
[84] "p20c"
[85] "p21a"
[86] "p21b"
[87] "p21c"
[88] "p22"
[89] "p23"
[90] "i_1_p24"
[91] "i_2_p24"
[92] "i_3_p24"
[93] "i_1_p25"
[94] "i_1_p26"
[95] "i_2_p25"
[96] "i_2_p26"
[97] "i_3_p25"
[98] "i_3_p26"
[99] "i_4_p25"
[100] "i_4_p26"
[101] "i_5_p25"
[102] "i_5_p26"
[103] "i_6_p25"
[104] "i_6_p26"
[105] "i_7_p25"
[106] "i_7_p26"
[107] "i_8_p25"
[108] "i_8_p26"
[109] "p25_otra1"
[110] "p27"
[111] "i_1_p28"
[112] "i_2_p28"
[113] "i_3_p28"
[114] "i_4_p28"
[115] "i_5_p28"
[116] "i_6_p28"
[117] "i_7_p28"
[118] "p29"
[119] "p30_o1"
[120] "p30_o2"
[121] "p30_o3"
[122] "p30_o4"
[123] "p30_o5"
[124] "p30_o6"
[125] "p31"
[126] "p32"
[127] "i_1_p33"
[128] "i_2_p33"
[129] "i_3_p33"
[130] "i_4_p33"
[131] "i_5_p33"
[132] "p34"
[133] "p35"
[134] "t_p36_1"
[135] "t_p36_2"
[136] "p37"
[137] "p38"
[138] "i_1_p39"
[139] "i_2_p39"
[140] "i_1_p40_o1"
[141] "i_1_p40_o2"
[142] "i_1_p40_o3"
[143] "i_1_p40_o4"
[144] "i_1_p40_o5"
[145] "i_1_p40_o6"
[146] "i_1_p40_o7"
[147] "i_1_p40_o8"
[148] "i_1_p40_o9"
[149] "i_1_p40_o10"
[150] "i_1_p40_o11"
[151] "i_2_p40_o1"
[152] "i_2_p40_o2"
[153] "i_2_p40_o3"
[154] "i_2_p40_o4"
[155] "i_2_p40_o5"
[156] "i_2_p40_o6"
[157] "i_2_p40_o7"
[158] "i_2_p40_o8"
[159] "i_2_p40_o9"
[160] "i_2_p40_o10"
[161] "i_2_p40_o11"
[162] "i_3_p40_o1"
[163] "i_3_p40_o2"
[164] "i_3_p40_o3"
[165] "i_3_p40_o4"
[166] "i_3_p40_o5"
[167] "i_3_p40_o6"
[168] "i_3_p40_o7"
[169] "i_3_p40_o8"
[170] "i_3_p40_o9"
[171] "i_3_p40_o10"
[172] "i_3_p40_o11"
[173] "i_1_p41"
[174] "i_2_p41"
[175] "i_3_p41"
[176] "i_4_p41"
[177] "i_5_p41"
[178] "p42"
[179] "p43"
[180] "p44"
[181] "p45"
[182] "p46"
[183] "p46_rec"
[184] "t_p47_1"
[185] "t_p47_2"
[186] "t_p47_3"
[187] "p48"
[188] "p49"
[189] "p50_o1"
[190] "p50_o2"
[191] "p50_o3"
[192] "p50_o4"
[193] "p50_o5"
[194] "p51"
[195] "p52"
[196] "p53"
[197] "p54"
[198] "p55"
[199] "p56"
[200] "p57_o1"
[201] "p57_o2"
[202] "p57_o3"
[203] "p57_o4"
[204] "p57_o5"
[205] "p57_o6"
[206] "p57_o7"
[207] "p57_o8"
[208] "p57_o9"
[209] "p57_o10"
[210] "p57_o11"
[211] "p57_o12"
[212] "p57_o13"
[213] "p57_o14"
[214] "p58"
[215] "q_128_s"
[216] "p59"
[217] "p59_otro"
[218] "p60"
[219] "q_130_s"
[220] "p61"
[221] "p62"
[222] "q_133_s"
[223] "p63"
[224] "q_134_s"
[225] "p64"
[226] "p65"
[227] "p66"
[228] "p66_det"
[229] "p67"
[230] "p68"
[231] "p69"
[232] "p70a"
[233] "p70b"
[234] "p70c"
[235] "p71"
[236] "p72a"
[237] "p72b"
[238] "p72c"
[239] "p73"
[240] "p74"
[241] "p75a"
[242] "p75b"
[243] "p75c"
[244] "p76"
[245] "p77"
[246] "p78"
[247] "p79a"
[248] "p79b"
[249] "p79c"
[250] "p80a"
[251] "p80b"
[252] "p80c"
[253] "p81"
[254] "p82"
[255] "p83"
[256] "p84"
[257] "p85"
[258] "p86"
[259] "p87"
[260] "p88"
[261] "p89"
[262] "p90"
[263] "p91"
[264] "p92"
[265] "p93"
[266] "p94"
[267] "p95"
[268] "p96"
[269] "p97"
[270] "p98"
[271] "p99"
[272] "p100"
[273] "p101a"
[274] "p101b"
[275] "p101c"
[276] "i_1_p102"
[277] "i_2_p102"
[278] "i_3_p102"
[279] "i_4_p102"
[280] "i_5_p102"
[281] "i_6_p102"
[282] "i_7_p102"
[283] "i_8_p102"
[284] "p103_o1"
[285] "p103_o2"
[286] "p103_o3"
[287] "p103_o4"
[288] "p103_o5"
[289] "p103_o6"
[290] "p103_o7"
[291] "p103_o8"
[292] "p103_o9"
[293] "s_p103_8"
[294] "p104_o1"
[295] "p104_o2"
[296] "p104_o3"
[297] "p104_o4"
[298] "p104_o5"
[299] "p104_o6"
[300] "p104_o7"
[301] "p104_o8"
[302] "p104_o9"
[303] "s_p104_8"
[304] "p105"
[305] "p106"
[306] "p107"
[307] "p108"
[308] "p109"
[309] "p110"
[310] "p111"
[311] "p112"
[312] "p113a"
[313] "p113b"
[314] "p114"
[315] "p115"
[316] "p116"
[317] "q_205_s"
[318] "p117"
[319] "p118"
[320] "q_207_s"
[321] "p119"
[322] "p120_o1"
[323] "p120_o2"
[324] "p120_o3"
[325] "p120_o4"
[326] "p120_o5"
[327] "p120_o6"
[328] "p120_o7"
[329] "p120_o8"
[330] "p120_o9"
[331] "p120_o10"
[332] "p120_o11"
[333] "p120_o12"
[334] "p120_o13"
[335] "p120_o14"
[336] "s_p120_13"
[337] "p121a"
[338] "p121b"
[339] "p121c"
[340] "p122"
[341] "q_213_s"
[342] "p123"
[343] "q_214_s"
[344] "p124"
[345] "p125_o1"
[346] "p125_o2"
[347] "p125_o3"
[348] "p125_o4"
[349] "p126"
[350] "p127"
[351] "p128"
[352] "p129"
[353] "p130"
[354] "p131"
[355] "q_222_s"
[356] "p132"
[357] "p133"
[358] "q_227_s"
[359] "p134"
[360] "q_228_s"
[361] "p135"
[362] "p136"
[363] "p137_o1"
[364] "p137_o2"
[365] "p137_o3"
[366] "p137_o4"
[367] "p138"
[368] "p139"
[369] "p140"
[370] "i_1_p141"
[371] "i_2_p141"
[372] "i_3_p141"
[373] "i_4_p141"
[374] "p141_otro"
[375] "p142"
[376] "p143_o1"
[377] "p143_o2"
[378] "p143_o3"
[379] "p143_o4"
[380] "p143_o5"
[381] "p143_o6"
[382] "p143_o7"
[383] "p143_o8"
[384] "p143_o9"
[385] "s_p143_8"
[386] "p144"
[387] "p145_o1"
[388] "p145_o2"
[389] "p145_o3"
[390] "p145_o4"
[391] "p145_o5"
[392] "p145_o6"
[393] "p145_o7"
[394] "p145_o8"
[395] "p145_o9"
[396] "p145_o10"
[397] "p145_o11"
[398] "p145_o12"
[399] "p146_o1"
[400] "p146_o2"
[401] "p146_o3"
[402] "p146_o4"
[403] "s_p146_3"
[404] "p147"
[405] "p148_o1"
[406] "p148_o2"
[407] "p148_o3"
[408] "p148_o4"
[409] "i_1_p149"
[410] "i_1_p150"
[411] "i_2_p149"
[412] "i_2_p150"
[413] "i_3_p149"
[414] "i_3_p150"
[415] "i_4_p149"
[416] "i_4_p150"
[417] "i_5_p149"
[418] "i_5_p150"
[419] "i_6_p149"
[420] "i_6_p150"
[421] "i_7_p149"
[422] "i_7_p150"
[423] "p153"
[424] "p154_o1"
[425] "p154_o2"
[426] "p154_o3"
[427] "p154_o4"
[428] "p154_o5"
[429] "p154_o6"
[430] "p154_o7"
[431] "p154_o8"
[432] "p154_o9"
[433] "p154_o10"
[434] "p154_o11"
[435] "p154_o12"
[436] "p154_o13"
[437] "s_p154_12"
[438] "p155"
[439] "q_250_s"
[440] "p156"
[441] "i_1_p157"
[442] "i_2_p157"
[443] "i_3_p157"
[444] "i_4_p157"
[445] "p158"
[446] "p159"
[447] "p160"
[448] "p161"
[449] "p162"
[450] "p163a_o1"
[451] "p163a_o2"
[452] "p163a_o3"
[453] "p163a_o4"
[454] "p163a_o5"
[455] "s_p163a_4"
[456] "p163b"
[457] "q_259_s"
[458] "p164"
[459] "p165"
[460] "q_261_s"
[461] "p166"
[462] "p167"
[463] "p168"
[464] "q_264_s"
[465] "p169"
[466] "p170"
[467] "p171"
[468] "p172"
[469] "p173"
[470] "p174"
[471] "p175"
[472] "p176"
[473] "p177_o1"
[474] "p177_o2"
[475] "p177_o3"
[476] "p177_o4"
[477] "p177_o5"
[478] "p177_o6"
[479] "p177_o7"
[480] "p177_o8"
[481] "s_p177_7"
[482] "p178_o1"
[483] "p178_o2"
[484] "p178_o3"
[485] "p178_o4"
[486] "p178_o5"
[487] "p178_o6"
[488] "s_p178_5"
[489] "i_1_p179"
[490] "i_2_p179"
[491] "i_3_p179"
[492] "i_4_p179"
[493] "p180"
[494] "p181_dia_termino"
[495] "p181_mes_termino"
[496] "p181_ano_termino"
[497] "p182_dia_no_termino"
[498] "p182_mes_no_termino"
[499] "p182_ano_no_termino"
[500] "p183"
[501] "p184"
[502] "p185"
[503] "p186"
[504] "p187"
[505] "p188"
[506] "p189"
[507] "p190"
[508] "p191"
[509] "p192"
[510] "p193"
[511] "p194"
[512] "p195"
[513] "i_1_p196"
[514] "i_2_p196"
[515] "p197"
[516] "p198"
[517] "q_295_s"
[518] "p199"
[519] "p200"
[520] "p201"
[521] "i_1_p202a"
[522] "i_1_p203a"
[523] "i_1_p204a"
[524] "i_1_p205a"
[525] "i_2_p202a"
[526] "i_2_p203a"
[527] "i_2_p204a"
[528] "i_2_p205a"
[529] "i_3_p202a"
[530] "i_3_p203a"
[531] "i_3_p204a"
[532] "i_3_p205a"
[533] "i_4_p202a"
[534] "i_4_p203a"
[535] "i_4_p204a"
[536] "i_4_p205a"
[537] "i_1_p202b"
[538] "i_1_p203b"
[539] "i_1_p204b"
[540] "i_2_p202b"
[541] "i_2_p203b"
[542] "i_2_p204b"
[543] "i_3_p202b"
[544] "i_3_p203b"
[545] "i_3_p204b"
[546] "i_4_p202b"
[547] "i_4_p203b"
[548] "i_4_p204b"
[549] "i_5_p202b"
[550] "i_5_p203b"
[551] "i_5_p204b"
[552] "i_6_p202b"
[553] "i_6_p203b"
[554] "i_6_p204b"
[555] "i_7_p202b"
[556] "i_7_p203b"
[557] "i_7_p204b"
[558] "p206"
[559] "q_307_s"
[560] "p207"
[561] "p208"
[562] "p209"
[563] "p210"
[564] "q_311_s"
[565] "p211_o1"
[566] "p211_o2"
[567] "p211_o3"
[568] "p211_o4"
[569] "p211_o5"
[570] "p211_o6"
[571] "p211_o7"
[572] "p211_o8"
[573] "s_p211_7"
[574] "i_1_p212"
[575] "i_2_p212"
[576] "i_3_p212"
[577] "i_4_p212"
[578] "i_5_p212"
[579] "i_6_p212"
[580] "p213"
[581] "p214"
[582] "p215"
[583] "p216"
[584] "p217"
[585] "p218"
[586] "p219"
[587] "p220"
[588] "p221"
[589] "p222"
[590] "p223"
[591] "p224a"
[592] "p224b"
[593] "p225"
[594] "q_327_s"
[595] "p226_o1"
[596] "p226_o2"
[597] "p226_o3"
[598] "p226_o4"
[599] "p226_o5"
[600] "s_p226_4"
[601] "p227"
[602] "p228"
[603] "p229"
[604] "p230"
[605] "p231"
[606] "p232"
[607] "p233"
[608] "p234"
[609] "p235"
[610] "i_1_p236_h"
[611] "i_1_p237_h"
[612] "i_2_p236_h"
[613] "i_2_p237_h"
[614] "i_3_p236_h"
[615] "i_3_p237_h"
[616] "i_4_p236_h"
[617] "i_4_p237_h"
[618] "i_5_p236_h"
[619] "i_5_p237_h"
[620] "i_1_p236_m"
[621] "i_1_p237_m"
[622] "i_3_p236_m"
[623] "i_3_p237_m"
[624] "i_4_p236_m"
[625] "i_4_p237_m"
[626] "i_6_p236_m"
[627] "i_6_p237_m"
[628] "p238"
[629] "p239_o1"
[630] "p239_o2"
[631] "p239_o3"
[632] "p239_o4"
[633] "p239_o5"
[634] "p239_o6"
[635] "p239_o7"
[636] "p239_o8"
[637] "p239_o9"
[638] "p239_o10"
[639] "p239_o11"
[640] "s_p239_10"
[641] "i_1_p240"
[642] "i_1_p241"
[643] "i_2_p240"
[644] "i_2_p241"
[645] "p240c"
[646] "p241c"
[647] "p242"
[648] "p243_o1"
[649] "p243_o2"
[650] "p243_o3"
[651] "p243_o4"
[652] "p243_o5"
[653] "p243_o6"
[654] "s_p243_5"
[655] "i_1_p244"
[656] "i_1_p245"
[657] "i_1_p246"
[658] "i_2_p244"
[659] "i_2_p245"
[660] "i_2_p246"
[661] "i_3_p244"
[662] "i_3_p245"
[663] "i_3_p246"
[664] "i_4_p244"
[665] "i_4_p245"
[666] "i_4_p246"
[667] "p247"
[668] "p248"
[669] "p249"
[670] "p250"
[671] "p251"
[672] "p252"
[673] "p253_o1"
[674] "p253_o2"
[675] "p253_o3"
[676] "p253_o4"
[677] "p253_o5"
[678] "p253_o6"
[679] "p253_o7"
[680] "p253_o8"
[681] "p253_o9"
[682] "p253_o10"
[683] "p253_o11"
[684] "p253_o12"
[685] "p253_o13"
[686] "p253_o14"
[687] "p253_o15"
[688] "p253_o16"
[689] "p253_o17"
[690] "p253_o18"
[691] "p253_o19"
[692] "s_p253_7"
[693] "p254"
[694] "p255"
[695] "p256"
[696] "p257"
[697] "p258"
[698] "p259_o1"
[699] "p259_o2"
[700] "p259_o3"
[701] "p259_o4"
[702] "p259_o5"
[703] "p259_o6"
[704] "p259_o7"
[705] "p259_o8"
[706] "p259_o9"
[707] "p259_o10"
[708] "p259_o11"
[709] "p259_o12"
[710] "p259_o13"
[711] "p259_o14"
[712] "p259_o15"
[713] "p259_o16"
[714] "p259_o17"
[715] "s_p259_4"
[716] "p260"
[717] "p261"
[718] "p262"
[719] "p263"
[720] "q_373_s"
[721] "p265"
[722] "q_374_s"
[723] "p267"
[724] "p268"
[725] "q_376_s"
[726] "p269"
[727] "p270"
[728] "p271"
[729] "p272"
[730] "p273"
[731] "p274"
[732] "p275"
[733] "p276"
[734] "p277"
[735] "p278"
[736] "p279"
[737] "p280"
[738] "p281"
[739] "q_389_s"
[740] "p282"
[741] "p283"
[742] "exp"
[743] "p284"
[744] "p285"
[745] "p286"
[746] "p287"
[747] "i_1_p288"
[748] "i_1_p289"
[749] "i_1_p290"
[750] "i_1_p291"
[751] "i_1_p292"
[752] "i_1_p293"
[753] "i_1_p294"
[754] "i_1_p295"
[755] "i_1_p296"
[756] "i_1_p297"
[757] "i_2_p288"
[758] "i_2_p289"
[759] "i_2_p290"
[760] "i_2_p291"
[761] "i_2_p292"
[762] "i_2_p293"
[763] "i_2_p294"
[764] "i_2_p295"
[765] "i_2_p296"
[766] "i_2_p297"
[767] "i_3_p288"
[768] "i_3_p289"
[769] "i_3_p290"
[770] "i_3_p291"
[771] "i_3_p292"
[772] "i_3_p293"
[773] "i_3_p294"
[774] "i_3_p295"
[775] "i_3_p296"
[776] "i_3_p297"
[777] "i_4_p288"
[778] "i_4_p289"
[779] "i_4_p290"
[780] "i_4_p291"
[781] "i_4_p292"
[782] "i_4_p293"
[783] "i_4_p294"
[784] "i_4_p295"
[785] "i_4_p296"
[786] "i_4_p297"
[787] "i_5_p288"
[788] "i_5_p289"
[789] "i_5_p290"
[790] "i_5_p291"
[791] "i_5_p292"
[792] "i_5_p293"
[793] "i_5_p294"
[794] "i_5_p295"
[795] "i_5_p296"
[796] "i_5_p297"
[797] "i_6_p288"
[798] "i_6_p289"
[799] "i_6_p290"
[800] "i_6_p291"
[801] "i_6_p292"
[802] "i_6_p293"
[803] "i_6_p294"
[804] "i_6_p295"
[805] "i_6_p296"
[806] "i_6_p297"
[807] "i_7_p288"
[808] "i_7_p289"
[809] "i_7_p290"
[810] "i_7_p291"
[811] "i_7_p292"
[812] "i_7_p293"
[813] "i_7_p294"
[814] "i_7_p295"
[815] "i_7_p296"
[816] "i_7_p297"
[817] "i_8_p288"
[818] "i_8_p289"
[819] "i_8_p290"
[820] "i_8_p291"
[821] "i_8_p292"
[822] "i_8_p293"
[823] "i_8_p294"
[824] "i_8_p295"
[825] "i_8_p296"
[826] "i_8_p297"
[827] "i_9_p288"
[828] "i_9_p289"
[829] "i_9_p290"
[830] "i_9_p291"
[831] "i_9_p292"
[832] "i_9_p293"
[833] "i_9_p294"
[834] "i_9_p295"
[835] "i_9_p296"
[836] "i_9_p297"
[837] "i_10_p288"
[838] "i_10_p289"
[839] "i_10_p290"
[840] "i_10_p291"
[841] "i_10_p292"
[842] "i_10_p293"
[843] "i_10_p294"
[844] "i_10_p295"
[845] "i_10_p296"
[846] "i_10_p297"
[847] "i_1_p298"
[848] "i_1_p299"
[849] "i_1_p300"
[850] "i_1_p301"
[851] "i_1_p302"
[852] "i_2_p298"
[853] "i_2_p299"
[854] "i_2_p300"
[855] "i_2_p301"
[856] "i_2_p302"
[857] "i_3_p298"
[858] "i_3_p299"
[859] "i_3_p300"
[860] "i_3_p301"
[861] "i_3_p302"
[862] "i_4_p298"
[863] "i_4_p299"
[864] "i_4_p300"
[865] "i_4_p301"
[866] "i_4_p302"
[867] "i_5_p298"
[868] "i_5_p299"
[869] "i_5_p300"
[870] "i_5_p301"
[871] "i_5_p302"
[872] "i_6_p298"
[873] "i_6_p299"
[874] "i_6_p300"
[875] "i_6_p301"
[876] "i_6_p302"
[877] "i_7_p298"
[878] "i_7_p299"
[879] "i_7_p300"
[880] "i_7_p301"
[881] "i_7_p302"
[882] "i_8_p298"
[883] "i_8_p299"
[884] "i_8_p300"
[885] "i_8_p301"
[886] "i_8_p302"
[887] "i_9_p298"
[888] "i_9_p299"
[889] "i_9_p300"
[890] "i_9_p301"
[891] "i_9_p302"
[892] "i_10_p298"
[893] "i_10_p299"
[894] "i_10_p300"
[895] "i_10_p301"
[896] "i_10_p302"
[897] "p303"
[898] "p304"
[899] "i_1_p305"
[900] "i_2_p305"
[901] "i_3_p305"
[902] "sel_1"
[903] "menores"
[904] "entre_18_29"
[905] "elegibles"
[906] "tramo_edad"
[907] "celda_sexo_edad"
[908] "educ"
[909] "w_personas_cal"
[910] "responde_modhogar"
[911] "tramo_edad_4"
[912] "celda_sexo_edad_hogar"
[913] "w_personas_cal_nr_mod_hogar"
[914] "varunit"
[915] "varstrat"
[916] "buena_salud"
[917] "relaciones_sexuales"
[918] "q_214_s_v2"
[919] "p25_otra1_v2"
[920] "p25_otra2_v2"
[921] "q_128_s_v2"
[922] "q_134_s_v2"
[923] "q_207_s_v2"
[924] "q_213_s_v2"
[925] "q_295_s_v2"
[926] "q_307_s_v2"
[927] "q_311_s_v2"
[928] "q_327_s_v2"
[929] "q_389_s_v2"
[930] "s_p120_13_v2"
[931] "s_p177_7_v2"
[932] "q_130_s_v2"
[933] "q_374_s_v2"
[934] "s_p211_7_v2"
[935] "q_227_s_v2"
[936] "q_228_s_v2"
[937] "fechaR"
[938] "edad"
[939] "fecha_nacimiento"
[940] "fecha_nacimiento_ano"
[941] "fecha_nacimiento_ano_ag"
[942] "fecha_nacimiento_ano_ag2"
[943] "edad5"
[944] "edad8"
[945] "edad13"
[946] "edad2"
[947] "edad4_pap"
[948] "p6_R"
[949] "p5_R"
[950] "educ12"
[951] "p8_R"
[952] "p284_R"
[953] "educ6"
[954] "educ3"
[955] "orientacion_sexual"
[956] "orientacion_sexual_separado"
[957] "pueblos"
[958] "prevision_salud"
[959] "genero"
[960] "genero_separada"
[961] "calidad_vida"
[962] "bienestar_vida_sexual"
[963] "salud_general"
[964] "mamografia_ult1"
[965] "mamografia_ult3"
[966] "mamografia_ult2"
[967] "pap_ult1"
[968] "pap_ult3"
[969] "antigeno_prostatico"
[970] "orgasmo"
[971] "homosexualidad"
[972] "sexo_amor"
[973] "comunicacion_sexual"
[974] "juego_sexual"
[975] "relacion_sexual_padre"
[976] "relacion_sexual_madre"
[977] "relacion_sexual_hermanos"
[978] "relacion_sexual_pareja"
[979] "relacion_sexual_amigos"
[980] "relacion_sexual_profesores"
[981] "relacion_sexual_profesionales_salud"
[982] "relacion_sexual_por_mi"
[983] "relacion_sexual_otras"
[984] "relacion_sin_duda"
[985] "relacion_no_sabe_no_responde"
[986] "relacion_sexual_hermanos_amigos"
[987] "edad_primer_beso"
[988] "iniciados_sexualmente"
[989] "edad_primera_rsex"
[990] "comunicacion_1rs"
[991] "condon_primera_rsex"
[992] "uso_condon"
[993] "anticonceptivas_primera_rsex"
[994] "condon_primera_rsex_motivo"
[995] "lugar_primera_rsex"
[996] "vinculo_primera_rsex"
[997] "hsh"
[998] "n_parejas_sexuales"
[999] "n_parejas_sexuales_ano"
[1000] "n_parejas_sexuales_mes"
[1001] "uso_condon_ultimo_ano"
[1002] "practicas_sexuales_vagina"
[1003] "practicas_sexuales_anal"
[1004] "practicas_sexuales_oral"
[1005] "p101_a"
[1006] "p101_b"
[1007] "p101_c"
[1008] "indicador"
[1009] "indicador2"
[1010] "repertorio_sexual_12m"
[1011] "rsex_alcohol"
[1012] "rsex_marihuana"
[1013] "rsex_drogas_otros"
[1014] "pago_rsex"
[1015] "ultima_rsexual"
[1016] "uso_condon_ultima_rsex_3m"
[1017] "uso_condon_ultima_rsex_12m"
[1018] "uso_anticonceptivas_ultima_rsex_3m"
[1019] "acceso_condon"
[1020] "satifaccion_ult_rsex"
[1021] "p151"
[1022] "p152"
[1023] "practicas_juzgadas"
[1024] "procedimientos_dolor"
[1025] "dif_edad"
[1026] "embarazo_no_planificado"
[1027] "numero_padres"
[1028] "depresion_parto_conjunta"
[1029] "edad_ultima_regla"
[1030] "p202_herpes"
[1031] "p202_tricomonas"
[1032] "p202_chlamydia"
[1033] "p202_gonorrea"
[1034] "p202_sifilis"
[1035] "p202_hepatitisB"
[1036] "p202_VPH_sola"
[1037] "p202_condiloma"
[1038] "p202_VPH_agregada"
[1039] "p202_VIH"
[1040] "p202_hepatitisC"
[1041] "its_alguna_vez"
[1042] "p203_herpes"
[1043] "p203_herpes_sin_na"
[1044] "p203_tricomonas"
[1045] "p203_tricomonas_sin_na"
[1046] "p203_candidiasis"
[1047] "p203_candidiasis_sin_na"
[1048] "p203_condiloma"
[1049] "p203_condiloma_sin_na"
[1050] "p203_chlamydia"
[1051] "p203_chlamydia_sin_na"
[1052] "p203_gonorrea"
[1053] "p203_gonorrea_sin_na"
[1054] "p203_sifilis"
[1055] "p203_sifilis_sin_na"
[1056] "p203_hepatitisB"
[1057] "p203_hepatitisB_sin_na"
[1058] "p203_VPH_sola"
[1059] "p203_VPH_sola_sin_na"
[1060] "p203_VIH"
[1061] "p203_VIH_sin_na"
[1062] "p203_hepatitisC"
[1063] "p203_hepatitisC_sin_na"
[1064] "dif_edad_herpes"
[1065] "dif_edad_tricomonas"
[1066] "dif_edad_candidiasis"
[1067] "dif_edad_condiloma"
[1068] "dif_edad_chlamydia"
[1069] "dif_edad_gonorrea"
[1070] "dif_edad_sifilis"
[1071] "dif_edad_hepatitisB"
[1072] "dif_edad_VPH_sola"
[1073] "dif_edad_VIH"
[1074] "dif_edad_hepatitisC"
[1075] "its_5_anos"
[1076] "edad_ultima_its"
[1077] "p211_no_riesgo"
[1078] "p211_pareja_unica"
[1079] "p211_no_sabe_donde"
[1080] "p211_no_importante"
[1081] "p211_temor_resultado"
[1082] "p211_verguenza"
[1083] "disfuncion_deseo"
[1084] "disfuncion_ereccion"
[1085] "disfuncion_orgasmo"
[1086] "acoso_piropos"
[1087] "acoso_agarrones"
[1088] "acoso_exhibicionismo"
[1089] "edad_acoso"
[1090] "p11_1_R"
[1091] "p11_2_R"
[1092] "p11_3_R"
[1093] "p11_4_R"
[1094] "phq4_num"
[1095] "phq4_cat"
[1096] "acuerdo_aborto"
[1097] "evaluacion_educacion_sexual"
[1098] "edad_abuso"
[1099] "abuso_padre_madre"
[1100] "abuso_padrastro_madrastra"
[1101] "abuso_tio_tia"
[1102] "abuso_abuelo_abuela"
[1103] "abuso_hermano_hermana"
[1104] "abuso_primo_prima"
[1105] "abuso_otro"
[1106] "abuso_pareja"
[1107] "abuso_amigo_amiga"
[1108] "abuso_companero_companera"
[1109] "abuso_otro_adolescente_conocido"
[1110] "abuso_vecino_a"
[1111] "abuso_amigo_a_padres"
[1112] "abuso_profesional_salud"
[1113] "abuso_profesor_escuela"
[1114] "abuso_pastor_sacerdote_monja"
[1115] "abuso_otro_adulto_conocido"
[1116] "abuso_un_desconocido"
[1117] "abuso_prefiere_no_responder"
[1118] "acoso_piropos2"
[1119] "acoso_agarrone2"
[1120] "acoso_exhibicionismo2"
[1121] "algun_acoso"
[1122] "interrumpir_embarazo"
[1123] "macro_region" Veamos el siguiente resultado:
P160. ¿Cuántos embarazos ha tenido a lo largo de su vida? incluya embarazos que terminaron en parto normal, parto prematuro, aborto, muerte fetal u otro problema.
Estimemos directamente en R:
# Resultado sin ponderar
mean(data$p160, na.rm=TRUE)[1] 2.761394Ahora ajustemos por el diseño muestral complejo:
# Ajustar el manejo de PSU solitarias
options(survey.lonely.psu = "adjust")
# Resultado ajustados por diseño muestral
svymean(~p160, design = enssex_design, na.rm = TRUE) mean SE
p160 2.8235 0.0338La estimación ponderada refleja la estructura de la población, mientras que la no ponderada refleja solo la muestra.
srvyrLa librería srvyr es una extensión de survey que permite trabajar con diseños muestrales complejos de una manera más sencilla y compatible con el enfoque tidyverse (como dplyr y ggplot2).
Tenemos que definir en diseño de mana similar:
enssex_srvyr <- data |>
as_survey_design(
ids = varunit, # UPM
strata = varstrat, # Estratos
weights = w_personas_cal, # Ponderador muestral
nest = TRUE
)Veamos un ejemplo:
enssex_srvyr |>
summarise(media_embarazos = survey_mean(p160, na.rm = TRUE))# A tibble: 1 × 2
media_embarazos media_embarazos_se
<dbl> <dbl>
1 2.82 0.0338Esto es mucho más potente para todo lo que implica análisis descriptivo y visualización de datos.
Vamos a trabajar los siguientes ejemplos:
enssex_srvyr |>
mutate(i_6_p9=if_else(i_6_p9==9, NA, i_6_p9)) |>
summarise(bienestar = survey_mean(i_6_p9, na.rm = TRUE))# A tibble: 1 × 2
bienestar bienestar_se
<dbl> <dbl>
1 5.08 0.0294enssex_srvyr |>
mutate(i_6_p9=if_else(i_6_p9==9, NA, i_6_p9)) |>
summarise(bienestar = survey_mean(i_6_p9, na.rm = TRUE, vartype = "ci"))# A tibble: 1 × 3
bienestar bienestar_low bienestar_upp
<dbl> <dbl> <dbl>
1 5.08 5.03 5.14enssex_srvyr |>
mutate(i_6_p9=if_else(i_6_p9==9, NA, i_6_p9)) |>
group_by(p1) |>
summarise(bienestar = survey_mean(i_6_p9, na.rm = TRUE, vartype = "ci"))# A tibble: 2 × 4
p1 bienestar bienestar_low bienestar_upp
<dbl+lbl> <dbl> <dbl> <dbl>
1 1 [Hombre] 5.35 5.27 5.42
2 2 [Mujer] 4.83 4.75 4.90enssex_srvyr |>
mutate(i_6_p9=if_else(i_6_p9==9, NA, i_6_p9)) |>
mutate(etario=case_when(
edad >= 18 & edad <=29 ~ "18 a 29 años",
edad >= 30 & edad <=39 ~ "30 a 39 años",
edad >= 40 & edad <=49 ~ "40 a 49 años",
edad >= 50 & edad <=59 ~ "50 a 59 años",
edad >= 60 ~ "60 o más años",
TRUE ~ NA
)) |>
mutate(etario = factor(etario, levels=c("18 a 29 años",
"30 a 39 años",
"40 a 49 años",
"50 a 59 años",
"60 o más años"))) |>
group_by(p1, etario) |>
summarise(bienestar = survey_mean(i_6_p9, na.rm = TRUE, vartype = "ci"))# A tibble: 10 × 5
# Groups: p1 [2]
p1 etario bienestar bienestar_low bienestar_upp
<dbl+lbl> <fct> <dbl> <dbl> <dbl>
1 1 [Hombre] 18 a 29 años 5.24 5.09 5.38
2 1 [Hombre] 30 a 39 años 5.76 5.65 5.87
3 1 [Hombre] 40 a 49 años 5.65 5.53 5.78
4 1 [Hombre] 50 a 59 años 5.46 5.33 5.60
5 1 [Hombre] 60 o más años 4.66 4.51 4.81
6 2 [Mujer] 18 a 29 años 5.34 5.24 5.44
7 2 [Mujer] 30 a 39 años 5.37 5.25 5.48
8 2 [Mujer] 40 a 49 años 5.21 5.07 5.36
9 2 [Mujer] 50 a 59 años 4.74 4.57 4.90
10 2 [Mujer] 60 o más años 3.55 3.41 3.69Comparamos errores estándar con y sin ponderadores:
# Sin diseño muestral
summary(lm(edad_primera_rsex ~ p1, data = data))
Call:
lm(formula = edad_primera_rsex ~ p1, data = data)
Residuals:
Min 1Q Median 3Q Max
-8.348 -2.348 -0.348 1.240 57.652
Coefficients:
Estimate Std. Error t value Pr(>|t|)
(Intercept) 15.17174 0.09512 159.5 <2e-16 ***
p1 1.58836 0.05497 28.9 <2e-16 ***
---
Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
Residual standard error: 3.454 on 17724 degrees of freedom
(2666 observations deleted due to missingness)
Multiple R-squared: 0.04499, Adjusted R-squared: 0.04494
F-statistic: 835 on 1 and 17724 DF, p-value: < 2.2e-16# Con diseño muestral
summary(svyglm(edad_primera_rsex~ p1, design = enssex_design))
Call:
svyglm(formula = edad_primera_rsex ~ p1, design = enssex_design)
Survey design:
svydesign(id = ~varunit, strata = ~varstrat, weights = ~w_personas_cal,
data = data, nest = TRUE, )
Coefficients:
Estimate Std. Error t value Pr(>|t|)
(Intercept) 15.33163 0.12328 124.36 <2e-16 ***
p1 1.53254 0.07214 21.24 <2e-16 ***
---
Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
(Dispersion parameter for gaussian family taken to be 11.59003)
Number of Fisher Scoring iterations: 2Ajustar por el diseño corrige los errores estándar.
Replique los siguiente resultados con las variables i_1_p9 a i_6_p9:
Replique los siguientes resultados
